README.md

ECCV2022-Paper-List

ECCV2022论文汇总，部分论文的详细解析见FightingCV公众号。

技术交流

欢迎大家关注公众号：FightingCV

FightingCV公众号	小助手微信 （备注【公司/学校+方向+ID】）

• 公众号每天都会进行论文、算法和代码的干货分享哦~

• 交流群每天分享一些最新的论文和解析，欢迎大家一起学习交流哈~~~ （加不进去可以加微信：775629340，记得备注【公司/学校+方向+ID】）

• 强烈推荐大家关注知乎账号和FightingCV公众号，可以快速了解到最新优质的干货资源。

数据集/Dataset

COO: Comic Onomatopoeia Dataset for Recognizing Arbitrary or Truncated Texts

• 论文/Paper: http://arxiv.org/pdf/2207.04675
• 代码/Code: https://github.com/ku21fan/COO-Comic-Onomatopoeia

Exploring Fine-Grained Audiovisual Categorization with the SSW60 Dataset

• 论文/Paper: http://arxiv.org/pdf/2207.10664
• 代码/Code: https://github.com/visipedia/ssw60

BRACE: The Breakdancing Competition Dataset for Dance Motion Synthesis

• 论文/Paper: http://arxiv.org/pdf/2207.10120
• 代码/Code: https://github.com/dmoltisanti/brace

CelebV-HQ: A Large-Scale Video Facial Attributes Dataset

• 论文/Paper: http://arxiv.org/pdf/2207.12393
• 代码/Code: https://github.com/CelebV-HQ/CelebV-HQ

Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions

• 论文/Paper: http://arxiv.org/pdf/2208.01166
• 代码/Code: None

Image Classification

Tree Structure-Aware Few-Shot Image Classification via Hierarchical Aggregation

• 论文/Paper: http://arxiv.org/pdf/2207.06989
• 代码/Code: https://github.com/remiMZ/HTS-ECCV22

Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization

• 论文/Paper: http://arxiv.org/pdf/2207.07818
• 代码/Code: https://github.com/zh460045050/BagCAMs

Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification

• 论文/Paper: http://arxiv.org/pdf/2207.09519
• 代码/Code: https://github.com/gaopengcuhk/tip-adapter

Invariant Feature Learning for Generalized Long-Tailed Classification

• 论文/Paper: http://arxiv.org/pdf/2207.09504
• 代码/Code: https://github.com/kaihuatang/generalized-long-tailed-benchmarks.pytorch

RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos

• 论文/Paper: http://arxiv.org/pdf/2207.11075
• 代码/Code: https://github.com/megvii-research/RealFlow

GAN

Ultra-high-resolution unpaired stain transformation via Kernelized Instance Normalization

• 论文/Paper: Waiting for official release
• 代码/Code: https://github.com/Kaminyou/URUST

Accelerating Score-based Generative Models with Preconditioned Diffusion Sampling

• 论文/Paper: http://arxiv.org/abs/2207.02196
• 代码/Code: https://github.com/fudan-zvg/pds

CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer

• 论文/Paper: http://arxiv.org/pdf/2207.04808
• 代码/Code: https://github.com/JarrentWu1031/CCPL

Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis

• 论文/Paper: http://arxiv.org/pdf/2207.05049
• 代码/Code: https://github.com/fast-vid2vid/fast-vid2vid

RepMix: Representation Mixing for Robust Attribution of Synthesized Images

• 论文/Paper: http://arxiv.org/abs/2207.02063
• 代码/Code: https://github.com/tubui/image_attribution

VecGAN: Image-to-Image Translation with Interpretable Latent Directions

• 论文/Paper: http://arxiv.org/pdf/2207.03411
• 代码/Code: None

Context-Consistent Semantic Image Editing with Style-Preserved Modulation

• 论文/Paper: http://arxiv.org/pdf/2207.06252
• 代码/Code: https://github.com/wuyangluo/spmpgan

DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation

• 论文/Paper: http://arxiv.org/pdf/2207.06124
• 代码/Code: https://github.com/huage001/dynast

Supervised Attribute Information Removal and Reconstruction for Image Manipulation

• 论文/Paper: http://arxiv.org/pdf/2207.06555
• 代码/Code: https://github.com/nannanli999/airr

Name: Adaptive Feature Interpolation for Low-Shot Image Generation

• 论文/Paper: https://arxiv.org/abs/2112.02450
• 代码/Code: https://github.com/dzld00/Adaptive-Feature-Interpolation-for-Low-Shot-Image-Generation

WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generation

• 论文/Paper: http://arxiv.org/pdf/2207.07288
• 代码/Code: Link:https://github.com/kobeshegu/ECCV2022_WaveGAN

FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs

• 论文/Paper: http://arxiv.org/pdf/2207.08630
• 代码/Code: https://github.com/iceli1007/FakeCLR

Outpainting by Queries

• 论文/Paper: https://arxiv.org/abs/2207.05312
• 代码/Code: https://github.com/Kaiseem/QueryOTR

Single Stage Virtual Try-on via Deformable Attention Flows

• 论文/Paper: http://arxiv.org/pdf/2207.09161
• 代码/Code: None

Structure-aware Editable Morphable Model for 3D Facial Detail Animation and Manipulation

• 论文/Paper: http://arxiv.org/pdf/2207.09019
• 代码/Code: https://github.com/gerwang/facial-detail-manipulation

Monocular 3D Object Reconstruction with GAN Inversion

• 论文/Paper: http://arxiv.org/pdf/2207.10061
• 代码/Code: https://github.com/junzhezhang/mesh-inversion

Generative Multiplane Images: Making a 2D GAN 3D-Aware

• 论文/Paper: http://arxiv.org/pdf/2207.10642
• 代码/Code: https://github.com/apple/ml-gmpi

DeltaGAN: Towards Diverse Few-shot Image Generation with Sample-Specific Delta

• 论文/Paper: http://arxiv.org/pdf/2207.10271
• 代码/Code: https://github.com/bcmi/deltagan-few-shot-image-generation

Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis

• 论文/Paper: http://arxiv.org/pdf/2207.10257
• 代码/Code: https://github.com/jgkwak95/surf-gan

SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.10256
• 代码/Code: None

2D GANs Meet Unsupervised Single-view 3D Reconstruction

• 论文/Paper: http://arxiv.org/pdf/2207.10183
• 代码/Code: None

InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images

• 论文/Paper: http://arxiv.org/pdf/2207.11148
• 代码/Code: None

Auto-regressive Image Synthesis with Integrated Quantization

• 论文/Paper: http://arxiv.org/pdf/2207.10776
• 代码/Code: None

Compositional Human-Scene Interaction Synthesis with Semantic Control

• 论文/Paper: http://arxiv.org/pdf/2207.12824
• 代码/Code: https://github.com/zkf1997/coins

Generator Knows What Discriminator Should Learn in Unconditional GANs

• 论文/Paper: http://arxiv.org/pdf/2207.13320
• 代码/Code: https://github.com/naver-ai/GGDR

StyleLight: HDR Panorama Generation for Lighting Estimation and Editing

• 论文/Paper: http://arxiv.org/pdf/2207.14811
• 代码/Code: https://github.com/Wanggcong/StyleLight

Cross Attention Based Style Distribution for Controllable Person Image Synthesis

• 论文/Paper: http://arxiv.org/pdf/2208.00712
• 代码/Code: None

NeRF

Streamable Neural Fields

• 论文/Paper: http://arxiv.org/pdf/2207.09663
• 代码/Code: https://github.com/jwcho5576/streamable_nf

Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis

• 论文/Paper: http://arxiv.org/pdf/2207.10257
• 代码/Code: https://github.com/jgkwak95/surf-gan

AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fields

• 论文/Paper: http://arxiv.org/pdf/2207.10312
• 代码/Code: None

PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereo

• 论文/Paper: http://arxiv.org/pdf/2207.11406
• 代码/Code: None

Neural-Sim: Learning to Generate Training Data with NeRF

• 论文/Paper: http://arxiv.org/pdf/2207.11368
• 代码/Code: None

Neural Density-Distance Fields

• 论文/Paper: http://arxiv.org/pdf/2207.14455
• 代码/Code: https://github.com/ueda0319/neddf

Visual Transformer

k-means Mask Transformer

• 论文/Paper: http://arxiv.org/pdf/2207.04044
• 代码/Code: https://github.com/google-research/deeplab2

Weakly Supervised Grounding for VQA in Vision-Language Transformers

• 论文/Paper: http://arxiv.org/pdf/2207.02334
• 代码/Code: https://github.com/aurooj/wsg-vqa-vltransformers

Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning

• 论文/Paper: http://arxiv.org/pdf/2207.04978
• 代码/Code: https://github.com/YehLi/ImageNetModel

CoMER: Modeling Coverage for Transformer-based Handwritten Mathematical Expression Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.04410
• 代码/Code: https://github.com/Green-Wood/CoMER

Towards Hard-Positive Query Mining for DETR-based Human-Object Interaction Detection

• 论文/Paper: http://arxiv.org/pdf/2207.05293
• 代码/Code: https://github.com/MuchHair/HQM

Hunting Group Clues with Transformers for Social Group Activity Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.05254
• 代码/Code: None

Entry-Flipped Transformer for Inference and Prediction of Participant Behavior

• 论文/Paper: http://arxiv.org/pdf/2207.06235
• 代码/Code: None

DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation

• 论文/Paper: http://arxiv.org/pdf/2207.06124
• 代码/Code: https://github.com/huage001/dynast

Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning

• 论文/Paper: http://arxiv.org/pdf/2207.06101
• 代码/Code: https://github.com/boeun-kim/gl-transformer

TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers

• 论文/Paper: http://arxiv.org/pdf/2207.08409
• 代码/Code: https://github.com/Sense-X/TokenMix

TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval

• 论文/Paper: http://arxiv.org/pdf/2207.07852
• 代码/Code: None

Action Quality Assessment with Temporal Parsing Transformer

• 论文/Paper: http://arxiv.org/pdf/2207.09270
• 代码/Code: None

GRIT: Faster and Better Image captioning Transformer Using Dual Visual Features

• 论文/Paper: http://arxiv.org/pdf/2207.09666
• 代码/Code: https://github.com/davidnvq/grit

Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning

• 论文/Paper: http://arxiv.org/pdf/2207.09644
• 代码/Code: None

AiATrack: Attention in Attention for Transformer Visual Tracking

• 论文/Paper: http://arxiv.org/pdf/2207.09603
• 代码/Code: https://github.com/Little-Podi/AiATrack

Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model

• 论文/Paper: http://arxiv.org/pdf/2207.10040
• 代码/Code: None

TinyViT: Fast Pretraining Distillation for Small Vision Transformers

• 论文/Paper: http://arxiv.org/pdf/2207.10666
• 代码/Code: https://github.com/microsoft/cream

An Efficient Spatio-Temporal Pyramid Transformer for Action Detection

• 论文/Paper: http://arxiv.org/pdf/2207.10448
• 代码/Code: None

Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration

• 论文/Paper: http://arxiv.org/pdf/2207.10447
• 代码/Code: https://github.com/164140757/scm

SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer

• 论文/Paper: http://arxiv.org/pdf/2207.10315
• 代码/Code: https://github.com/hrzhou2/seedformer

Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.10866
• 代码/Code: None

IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.12100
• 代码/Code: None

3D Siamese Transformer Network for Single Object Tracking on Point Clouds

• 论文/Paper: http://arxiv.org/pdf/2207.11995
• 代码/Code: None

Reference-based Image Super-Resolution with Deformable Attention Transformer

• 论文/Paper: http://arxiv.org/pdf/2207.11938
• 代码/Code: None

SiRi: A Simple Selective Retraining Mechanism for Transformer-based Visual Grounding

• 论文/Paper: http://arxiv.org/pdf/2207.13325
• 代码/Code: None

Online Continual Learning with Contrastive Vision Transformer

• 论文/Paper: http://arxiv.org/pdf/2207.13516
• 代码/Code: None

Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers

• 论文/Paper: http://arxiv.org/pdf/2207.13820
• 代码/Code: https://github.com/postech-ami/FastMETRO

Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition

• 论文/Paper: http://arxiv.org/pdf/2208.00438
• 代码/Code: https://github.com/xdxie/WordArt

多模态 / Multimodal

Audio-Visual Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.05042
• 代码/Code: https://github.com/OpenNLPLab/AVSBench

Cross-modal Prototype Driven Network for Radiology Report Generation

• 论文/Paper: http://arxiv.org/pdf/2207.04818
• 代码/Code: None

Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecasting

• 论文/Paper: http://arxiv.org/pdf/2207.04624
• 代码/Code: https://github.com/d1024choi/HLSTrajForecast

UniNet: Unified Architecture Search with Convolution, Transformer, and MLP

• 论文/Paper: http://arxiv.org/pdf/2207.05420
• 代码/Code: https://github.com/Sense-X/UniNet

Video Graph Transformer for Video Question Answering

• 论文/Paper: http://arxiv.org/pdf/2207.05342
• 代码/Code: https://github.com/sail-sg/VGT

Bootstrapped Masked Autoencoders for Vision BERT Pretraining

• 论文/Paper: http://arxiv.org/pdf/2207.07116
• 代码/Code: https://github.com/lightdxy/bootmae

Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution

• 论文/Paper: http://arxiv.org/pdf/2207.09156
• 代码/Code: None

Exploiting Unlabeled Data with Vision and Language Models for Object Detection

• 论文/Paper: http://arxiv.org/pdf/2207.08954
• 代码/Code: https://github.com/xiaofeng94/VL-PLM

LocVTP: Video-Text Pre-training for Temporal Localization

• 论文/Paper: http://arxiv.org/pdf/2207.10362
• 代码/Code: https://github.com/mengcaopku/locvtp

Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments

• 论文/Paper: http://arxiv.org/pdf/2207.10785
• 代码/Code: https://github.com/VinAIResearch/fsvc-ata

Cross-Modal 3D Shape Generation and Manipulation

• 论文/Paper: http://arxiv.org/pdf/2207.11795
• 代码/Code: None

Learning Visual Representation from Modality-Shared Contrastive Language-Image Pre-training

• 论文/Paper: http://arxiv.org/pdf/2207.12661
• 代码/Code: https://github.com/hxyou/msclip

对比学习/Contrastive Learning

Network Binarization via Contrastive Learning

• 论文/Paper: http://arxiv.org/pdf/2207.02970
• 代码/Code: None

Contrastive Deep Supervision

• 论文/Paper: http://arxiv.org/pdf/2207.05306
• 代码/Code: None

ConCL: Concept Contrastive Learning for Dense Prediction Pre-training in Pathology Images

• 论文/Paper: http://arxiv.org/pdf/2207.06733
• 代码/Code: https://github.com/tencentailabhealthcare/concl

Action-based Contrastive Learning for Trajectory Prediction

• 论文/Paper: http://arxiv.org/pdf/2207.08664
• 代码/Code: None

FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs

• 论文/Paper: http://arxiv.org/pdf/2207.08630
• 代码/Code: https://github.com/iceli1007/FakeCLR.

Adversarial Contrastive Learning via Asymmetric InfoNCE

• 论文/Paper: http://arxiv.org/pdf/2207.08374
• 代码/Code: https://github.com/yqy2001/A-InfoNCE

Fast-MoCo: Boost Momentum-based Contrastive Learning with Combinatorial Patches

• 论文/Paper: http://arxiv.org/pdf/2207.08220
• 代码/Code: None

Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness

• 论文/Paper: http://arxiv.org/pdf/2207.10899
• 代码/Code: https://github.com/pantheon5100/DeACL.

Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.10892
• 代码/Code: None

目标检测/Object Detection

Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection

• 论文/Paper: http://arxiv.org/pdf/2207.02541
• 代码/Code: None

Should All Proposals be Treated Equally in Object Detection?

• 论文/Paper: http://arxiv.org/pdf/2207.03520
• 代码/Code: None

HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors

• 论文/Paper: http://arxiv.org/pdf/2207.05345
• 代码/Code: https://github.com/LutingWang/HEAD

Adversarially-Aware Robust Object Detector

• 论文/Paper: http://arxiv.org/pdf/2207.06202
• 代码/Code: https://github.com/7eu7d7/robustdet

ObjectBox: From Centers to Boxes for Anchor-Free Object Detection

• 论文/Paper: http://arxiv.org/pdf/2207.06985
• 代码/Code: https://github.com/mohsenzand/objectbox

Point-to-Box Network for Accurate Object Detection via Single Point Supervision

• 论文/Paper: http://arxiv.org/pdf/2207.06827
• 代码/Code: None

DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection

• 论文/Paper: http://arxiv.org/pdf/2207.08531
• 代码/Code: https://github.com/SPengLiang/DID-M3D.

SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection

• 论文/Paper: http://arxiv.org/pdf/2207.07898
• 代码/Code: https://github.com/Hydragon516/SPSN

Rethinking IoU-based Optimization for Single-stage 3D Object Detection

• 论文/Paper: http://arxiv.org/pdf/2207.09332
• 代码/Code: https://github.com/hlsheng1/RDIoU

Densely Constrained Depth Estimator for Monocular 3D Object Detection

• 论文/Paper: http://arxiv.org/pdf/2207.10047
• 代码/Code: https://github.com/bravegroup/dcd

Robust Object Detection With Inaccurate Bounding Boxes

• 论文/Paper: http://arxiv.org/pdf/2207.09697
• 代码/Code: https://github.com/cxliu0/OA-MIL

Unsupervised Domain Adaptation for One-stage Object Detector using Offsets to Bounding Box

• 论文/Paper: http://arxiv.org/pdf/2207.09656
• 代码/Code: None

AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection

• 论文/Paper: http://arxiv.org/pdf/2207.10316
• 代码/Code: https://github.com/zehuichen123/autoalignv2

Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark

• 论文/Paper: http://arxiv.org/pdf/2207.11169
• 代码/Code: https://github.com/amazon-research/few-shot-object-detection-benchmark.

DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection

• 论文/Paper: http://arxiv.org/pdf/2207.10758
• 代码/Code: https://github.com/abhi1kumar/DEVIANT

Active Learning Strategies for Weakly-supervised Object Detection

• 论文/Paper: http://arxiv.org/pdf/2207.12112
• 代码/Code: https://github.com/huyvvo/BiB.

W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection

• 论文/Paper: http://arxiv.org/pdf/2207.12104
• 代码/Code: https://github.com/1170300714/w2n_wsod.

Salient Object Detection for Point Clouds

• 论文/Paper: http://arxiv.org/pdf/2207.11889
• 代码/Code: None

UC-OWOD: Unknown-Classified Open World Object Detection

• 论文/Paper: http://arxiv.org/pdf/2207.11455
• 代码/Code: https://github.com/JohnWuzh/UC-OWOD

Monocular 3D Object Detection with Depth from Motion

• 论文/Paper: http://arxiv.org/pdf/2207.12988
• 代码/Code: https://github.com/tai-wang/depth-from-motion

目标跟踪/Object Tracking

Tracking Objects as Pixel-wise Distributions

• 论文/Paper: http://arxiv.org/pdf/2207.05518
• 代码/Code: None

Towards Grand Unification of Object Tracking

• 论文/Paper: http://arxiv.org/pdf/2207.07078
• 代码/Code: https://github.com/masterbin-iiau/unicorn

The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Counting

• 论文/Paper: http://arxiv.org/pdf/2207.09295
• 代码/Code: None

MOTCOM: The Multi-Object Tracking Dataset Complexity Metric

• 论文/Paper: http://arxiv.org/pdf/2207.10031
• 代码/Code: None

Robust Landmark-based Stent Tracking in X-ray Fluoroscopy

• 论文/Paper: http://arxiv.org/pdf/2207.09933
• 代码/Code: None

AiATrack: Attention in Attention for Transformer Visual Tracking

• 论文/Paper: http://arxiv.org/pdf/2207.09603
• 代码/Code: https://github.com/Little-Podi/AiATrack

3D Siamese Transformer Network for Single Object Tracking on Point Clouds

• 论文/Paper: http://arxiv.org/pdf/2207.11995
• 代码/Code: None

Tracking Every Thing in the Wild

• 论文/Paper: http://arxiv.org/pdf/2207.12978
• 代码/Code: None

AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing

• 论文/Paper: http://arxiv.org/pdf/2207.13784
• 代码/Code: https://github.com/eth-siplab/AvatarPoser

语义分割/Segmentation

Domain Adaptive Video Segmentation via Temporal Pseudo Supervision

• 论文/Paper: http://arxiv.org/pdf/2207.02372
• 代码/Code: https://github.com/xing0047/tps

OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers

• 论文/Paper: http://arxiv.org/pdf/2207.02255
• 代码/Code: https://github.com/pjlallen/osformer

PseudoClick: Interactive Image Segmentation with Click Imitation

• 论文/Paper: http://arxiv.org/pdf/2207.05282
• 代码/Code: None

XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

• 论文/Paper: http://arxiv.org/pdf/2207.07115
• 代码/Code: https://github.com/hkchengrex/XMem

Tackling Background Distraction in Video Object Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.06953
• 代码/Code: https://github.com/suhwan-cho/tbd

Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.08549
• 代码/Code: None

Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.08485
• 代码/Code: https://github.com/NUST-Machine-Intelligence-Laboratory/HFAN

Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding

• 论文/Paper: http://arxiv.org/pdf/2207.08455
• 代码/Code: None

Learning Quality-aware Dynamic Memory for Video Object Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.07922
• 代码/Code: https://github.com/workforai/QDMN

Box-supervised Instance Segmentation with Level Set Evolution

• 论文/Paper: http://arxiv.org/pdf/2207.09055
• 代码/Code: https://github.com/LiWentomng/boxlevelset

ML-BPM: Multi-teacher Learning with Bidirectional Photometric Mixing for Open Compound Domain Adaptation in Semantic Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.09045
• 代码/Code: None

Self-Supervised Interactive Object Segmentation Through a Singulation-and-Grasping Approach

• 论文/Paper: http://arxiv.org/pdf/2207.09314
• 代码/Code: None

DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.09988
• 代码/Code: https://github.com/dvlab-research/decouplenet

CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.09778
• 代码/Code: https://github.com/saltoricristiano/cosmix-uda

GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.09763
• 代码/Code: https://github.com/saltoricristiano/gipso-sfouda

Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions

• 论文/Paper: http://arxiv.org/pdf/2207.10667
• 代码/Code: https://github.com/theo2021/onda

In Defense of Online Models for Video Instance Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.10661
• 代码/Code: https://github.com/wjf5203/vnext

Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.10436
• 代码/Code: https://github.com/guoleisun/vss-mrcfa

Long-tailed Instance Segmentation using Gumbel Optimized Loss

• 论文/Paper: http://arxiv.org/pdf/2207.10936
• 代码/Code: https://github.com/kostas1515/GOL

Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.10892
• 代码/Code: None

Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.10866
• 代码/Code: None

Self-Support Few-Shot Semantic Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.11549
• 代码/Code: https://github.com/fanq15/SSP

Active Pointly-Supervised Instance Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.11493
• 代码/Code: None

Video Mask Transfiner for High-Quality Video Instance Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.14012
• 代码/Code: None

Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation

• 论文/Paper: http://arxiv.org/pdf/2208.00306
• 代码/Code: None

Per-Clip Video Object Segmentation

• 论文/Paper: http://arxiv.org/pdf/2208.01924
• 代码/Code: https://github.com/pkyong95/PCVOS

Cluster-to-adapt: Few Shot Domain Adaptation for Semantic Segmentation across Disjoint Labels

• 论文/Paper: http://arxiv.org/pdf/2208.02804
• 代码/Code: None

医学图像分割/Medical Image Segmentation

Personalizing Federated Medical Image Segmentation via Local Calibration

• 论文/Paper: http://arxiv.org/pdf/2207.04655
• 代码/Code: https://github.com/jcwang123/FedLC

Learning Topological Interactions for Multi-Class Medical Image Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.09654
• 代码/Code: https://github.com/topoxlab/topointeraction

Knowledge Distillation

Knowledge Condensation Distillation

• 论文/Paper: http://arxiv.org/pdf/2207.05409
• 代码/Code: https://github.com/dzy3/KCD

FedX: Unsupervised Federated Learning with Cross Knowledge Distillation

• 论文/Paper: http://arxiv.org/pdf/2207.09158
• 代码/Code: None

Action Detection

ReAct: Temporal Action Detection with Relational Queries

• 论文/Paper: http://arxiv.org/pdf/2207.07097
• 代码/Code: https://github.com/sssste/react

Semi-Supervised Temporal Action Detection with Proposal-Free Masking

• 论文/Paper: http://arxiv.org/pdf/2207.07059
• 代码/Code: https://github.com/sauradip/SPOT

Temporal Action Detection with Global Segmentation Mask Learning

• 论文/Paper: http://arxiv.org/pdf/2207.06580
• 代码/Code: https://github.com/sauradip/TAGS

Weakly-Supervised Temporal Action Detection for Fine-Grained Videos with Hierarchical Atomic Actions

• 论文/Paper: http://arxiv.org/pdf/2207.11805
• 代码/Code: None

Action Recognition

Compound Prototype Matching for Few-shot Action Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.05515
• 代码/Code: None

Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.09767
• 代码/Code: https://github.com/canbaoburen/CoDT

Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition

• 论文/Paper: http://arxiv.org/pdf/2208.01897
• 代码/Code: None

Anomaly Detection

Registration based Few-Shot Anomaly Detection

• 论文/Paper: http://arxiv.org/pdf/2207.07361
• 代码/Code: https://github.com/MediaBrain-SJTU/RegAD

Look at Adjacent Frames: Video Anomaly Detection without Offline Training

• 论文/Paper: http://arxiv.org/pdf/2207.13798
• 代码/Code: None

人脸识别/Face Recognition

Controllable and Guided Face Synthesis for Unconstrained Face Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.10180
• 代码/Code: None

人体姿态估计/Human Pose Estimation

Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation

• 论文/Paper: http://arxiv.org/pdf/2207.02425
• 代码/Code: None

Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks

• 论文/Paper: http://arxiv.org/pdf/2207.05444
• 代码/Code: https://github.com/JiehongLin/Self-DPDN

Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning

• 论文/Paper: http://arxiv.org/pdf/2207.06101
• 代码/Code: https://github.com/boeun-kim/gl-transformer

TransGrasp: Grasp Pose Estimation of a Category of Objects by Transferring Grasps from Only One Labeled Instance

• 论文/Paper: http://arxiv.org/pdf/2207.07861
• 代码/Code: https://github.com/yanjh97/TransGrasp

Pose for Everything: Towards Category-Agnostic Pose Estimation

• 论文/Paper: http://arxiv.org/pdf/2207.10387
• 代码/Code: https://github.com/luminxu/Pose-for-Everything

C3P: Cross-domain Pose Prior Propagation for Weakly Supervised 3D Human Pose Estimation

• 论文/Paper: None
• 代码/Code: https://github.com/wucunlin/C3P

3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal

• 论文/Paper: http://arxiv.org/pdf/2207.11061
• 代码/Code: https://github.com/MengHao666/HDR.

Faster VoxelPose: Real-time 3D Human Pose Estimation by Orthographic Projection

• 论文/Paper: http://arxiv.org/pdf/2207.10955
• 代码/Code: None

ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization

• 论文/Paper: http://arxiv.org/pdf/2207.13691
• 代码/Code: None

RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation

• 论文/Paper: http://arxiv.org/pdf/2208.00237
• 代码/Code: None

Neural Correspondence Field for Object Pose Estimation

• 论文/Paper: http://arxiv.org/pdf/2208.00113
• 代码/Code: None

Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimation

• 论文/Paper: http://arxiv.org/pdf/2208.00090
• 代码/Code: None

CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation

• 论文/Paper: http://arxiv.org/pdf/2208.00571
• 代码/Code: https://github.com/huawei-noah/noah-research/tree/master/CLIFF

人脸活体检测/Face Anti-Spoofing

Generative Domain Adaptation for Face Anti-Spoofing

• 论文/Paper: http://arxiv.org/pdf/2207.10015
• 代码/Code: None

人脸属性识别/Facial Attribute Recognition

FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification

• 论文/Paper: http://arxiv.org/pdf/2207.10888
• 代码/Code: https://github.com/Bernardo1998/FairGRAPE

人脸相关 / Face

On Mitigating Hard Clusters for Face Clustering

• 论文/Paper: http://arxiv.org/pdf/2207.11895
• 代码/Code: https://github.com/echoanran/On-Mitigating-Hard-Clusters.

Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis

• 论文/Paper: http://arxiv.org/pdf/2207.11770
• 代码/Code: None

Human Reconstruction

3D Clothed Human Reconstruction in the Wild

• 论文/Paper: http://arxiv.org/pdf/2207.10053
• 代码/Code: https://github.com/hygenie1228/clothwild_release

UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation

• 论文/Paper: http://arxiv.org/pdf/2207.09835
• 代码/Code: https://github.com/ShenhanQian/UNIF

The One Where They Reconstructed 3D Humans and Environments in TV Shows

• 论文/Paper: http://arxiv.org/pdf/2207.14279
• 代码/Code: None

Relighting

Geometry-aware Single-image Full-body Human Relighting

• 论文/Paper: http://arxiv.org/pdf/2207.04750
• 代码/Code: None

Relighting4D: Neural Relightable Human from Videos

• 论文/Paper: http://arxiv.org/pdf/2207.07104
• 代码/Code: https://github.com/FrozenBurning/Relighting4D

DeepFake

Detecting and Recovering Sequential DeepFake Manipulation

• 论文/Paper: http://arxiv.org/abs/2207.02204
• 代码/Code: https://github.com/rshaojimmy/seqdeepfake

An Efficient Method for Face Quality Assessment on the Edge

• 论文/Paper: http://arxiv.org/pdf/2207.09505
• 代码/Code: None

Text Recognition

Scene Text Recognition with Permuted Autoregressive Sequence Models

• 论文/Paper: http://arxiv.org/pdf/2207.06966
• 代码/Code: https://github.com/baudm/parseq

Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting

• 论文/Paper: http://arxiv.org/pdf/2207.06694
• 代码/Code: https://github.com/hikopensource/davar-lab-ocr

Contextual Text Block Detection towards Scene Text Understanding

• 论文/Paper: http://arxiv.org/pdf/2207.12955
• 代码/Code: None

点云/Point Cloud

Open-world Semantic Segmentation for LIDAR Point Clouds

• 论文/Paper: http://arxiv.org/pdf/2207.01452
• 代码/Code: https://github.com/jun-cen/open_world_3d_semantic_segmentation

2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds

• 论文/Paper: http://arxiv.org/pdf/2207.04397
• 代码/Code: None

CPO: Change Robust Panorama to Point Cloud Localization

• 论文/Paper: http://arxiv.org/pdf/2207.05317
• 代码/Code: None

diffConv: Analyzing Irregular Point Clouds with an Irregular View

• 论文/Paper: https://arxiv.org/abs/2111.14658
• 代码/Code: https://github.com/mmmmimic/diffConvNet

CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement

• 论文/Paper: http://arxiv.org/pdf/2207.08082
• 代码/Code: None

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation

• 论文/Paper: http://arxiv.org/pdf/2207.09084
• 代码/Code: None

SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer

• 论文/Paper: http://arxiv.org/pdf/2207.10315
• 代码/Code: https://github.com/hrzhou2/seedformer

Dynamic 3D Scene Analysis by Point Cloud Accumulation

• 论文/Paper: http://arxiv.org/pdf/2207.12394
• 代码/Code: None

3D Siamese Transformer Network for Single Object Tracking on Point Clouds

• 论文/Paper: http://arxiv.org/pdf/2207.11995
• 代码/Code: None

Salient Object Detection for Point Clouds

• 论文/Paper: http://arxiv.org/pdf/2207.11889
• 代码/Code: None

MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud

• 论文/Paper: http://arxiv.org/pdf/2207.14268
• 代码/Code: https://github.com/MichaelRamamonjisoa/MonteBoxFinder

光流估计/Flow Estimation

Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation

• 论文/Paper: http://arxiv.org/pdf/2207.07522
• 代码/Code: https://github.com/cwc1260/BiFlow

What Matters for 3D Scene Flow Network

• 论文/Paper: http://arxiv.org/pdf/2207.09143
• 代码/Code: https://github.com/IRMVLab/3DFlow

Deep 360$^\circ$ Optical Flow Estimation Based on Multi-Projection Fusion

• 论文/Paper: http://arxiv.org/pdf/2208.00776
• 代码/Code: None

深度估计/Depth Estimation

Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches

• 论文/Paper: http://arxiv.org/pdf/2207.04718
• 代码/Code: None

Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics

• 论文/Paper: http://arxiv.org/pdf/2207.04680
• 代码/Code: https://github.com/SenZHANG-GitHub/ekf-imu-depth

RA-Depth: Resolution Adaptive Self-Supervised Monocular Depth Estimation

• 论文/Paper: http://arxiv.org/pdf/2207.11984
• 代码/Code: None

车道线检测/Lane Detection

RCLane: Relay Chain Prediction for Lane Detection

• 论文/Paper: http://arxiv.org/pdf/2207.09399
• 代码/Code: None

轨迹预测/Trajectory Prediction

Action-based Contrastive Learning for Trajectory Prediction

• 论文/Paper: http://arxiv.org/pdf/2207.08664
• 代码/Code: None

Learning Pedestrian Group Representations for Multi-modal Trajectory Prediction

• 论文/Paper: http://arxiv.org/pdf/2207.09953
• 代码/Code: https://github.com/inhwanbae/gpgraph

Aware of the History: Trajectory Forecasting with the Local Behavior Data

• 论文/Paper: http://arxiv.org/pdf/2207.09646
• 代码/Code: None

Human Trajectory Prediction via Neural Social Physics

• 论文/Paper: http://arxiv.org/pdf/2207.10435
• 代码/Code: https://github.com/realcrane/human-trajectory-prediction-via-neural-social-physics

D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights

• 论文/Paper: http://arxiv.org/pdf/2207.10398
• 代码/Code: https://github.com/vtp-tl/d2-tpred

超分/Super-Resolution

Image Super-Resolution with Deep Dictionary

• 论文/Paper: http://arxiv.org/pdf/2207.09228
• 代码/Code: None

Learning Mutual Modulation for Self-Supervised Cross-Modal Super-Resolution

• 论文/Paper: http://arxiv.org/pdf/2207.09156
• 代码/Code: None

CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution

• 论文/Paper: http://arxiv.org/pdf/2207.10345
• 代码/Code: https://github.com/cheeun/cadyq

Towards Interpretable Video Super-Resolution via Alternating Optimization

• 论文/Paper: http://arxiv.org/pdf/2207.10765
• 代码/Code: None

Reference-based Image Super-Resolution with Deformable Attention Transformer

• 论文/Paper: http://arxiv.org/pdf/2207.11938
• 代码/Code: None

图像去噪/Image Denoising

Optimizing Image Compression via Joint Learning with Denoising

• 论文/Paper: http://arxiv.org/pdf/2207.10869
• 代码/Code: https://github.com/felixcheng97/DenoiseCompression

图像去模糊/Image Deblurring

Spatio-Temporal Deformable Attention Network for Video Deblurring

• 论文/Paper: http://arxiv.org/pdf/2207.10852
• 代码/Code: None

Efficient Video Deblurring Guided by Motion Magnitude

• 论文/Paper: http://arxiv.org/pdf/2207.13374
• 代码/Code: None

图像复原/Image Restoration

D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration

• 论文/Paper: http://arxiv.org/pdf/2207.03294
• 代码/Code: https://github.com/zhaoyuzhi/D2HNet

图像增强/Image Enhancement

Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression

• 论文/Paper: http://arxiv.org/pdf/2207.10564
• 代码/Code: https://github.com/jinyeying/night-enhancement

检索/Image Retrieval

Feature Representation Learning for Unsupervised Cross-domain Image Retrieval

• 论文/Paper: http://arxiv.org/pdf/2207.09721
• 代码/Code: https://github.com/conghuihu/ucdir

2D目标检测(2D Object Detection)

[4] Multimodal Object Detection via Probabilistic Ensembling (基于概率集成的多模态目标检测) (Oral)

paper | code

[3] Point-to-Box Network for Accurate Object Detection via Single Point Supervision (通过单点监督实现精确目标检测的点对盒网络)
paper | code

[2] You Should Look at All Objects (您应该查看所有物体)
paper | code

[1] Adversarially-Aware Robust Object Detector (对抗性感知鲁棒目标检测器)(Oral))
paper | code

3D目标检测(3D Object Detection)

[2] Densely Constrained Depth Estimator for Monocular 3D Object Detection (用于单目 3D 目标检测的密集约束深度估计器)
paper | code

[1] Rethinking IoU-based Optimization for Single-stage 3D Object Detection (重新思考基于 IoU 的单阶段 3D 对象检测优化)
paper

人物交互检测(HOI Detection)

[2] Discovering Human-Object Interaction Concepts via Self-Compositional Learning (通过自组合学习发现人-物交互概念)

paper | [code](https://github.com/zhihou7/scl; https://github.com/zhihou7/HOI-CL)

[1] Towards Hard-Positive Query Mining for DETR-based Human-Object Interaction Detection (面向基于 DETR 的人机交互检测的硬性查询挖掘)
paper | code

显著性目标检测(Saliency Object Detection)

[1] KD-SCFNet: Towards More Accurate and Efficient Salient Object Detection via Knowledge Distillation (KD-SCFNet：通过知识蒸馏实现更准确、更高效的显着目标检测)

paper | code

图像异常检测/表面缺陷检测(Anomally Detection in Image)

[2] DSR -- A dual subspace re-projection network for surface anomaly detection (DSR——用于表面异常检测的双子空间重投影网络)

paper | code

[1] DICE: Leveraging Sparsification for Out-of-Distribution Detection (DICE：利用稀疏化进行分布外检测)
paper | code

实例分割(Instance Segmentation)

[3] In Defense of Online Models for Video Instance Segmentation (为视频实例分割的在线模型辩护) (Oral)
paper|code

[2] Box-supervised Instance Segmentation with Level Set Evolution (具有水平集进化的框监督实例分割)
paper

[1] OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers (OSFormer：使用 Transformers 进行单阶段伪装实例分割)
paper | code

语义分割(Semantic Segmentation)

[1] 2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds (2DPASS：激光雷达点云上的二维先验辅助语义分割)
paper | code

视频目标分割(Video Object Segmentation)

[1] Learning Quality-aware Dynamic Memory for Video Object Segmentation (视频对象分割的学习质量感知动态内存)
paper | code

超分辨率(Super Resolution)

[3] Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution (学习高效图像超分辨率的串并行查找表)

paper | code

[2] Efficient Meta-Tuning for Content-aware Neural Video Delivery (内容感知神经视频交付的高效元调整)
paper | code

[1] Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks (超低精度超分辨率网络的动态双可训练边界)
paper | code

图像复原/图像增强/图像重建(Image Restoration/Image Reconstruction)

[9] Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression (无监督夜间图像增强：当层分解遇到光效抑制时)

paper | code

[8] Bringing Rolling Shutter Images Alive with Dual Reversed Distortion(通过双重反转失真使滚动快门图像重现) (Oral)
paper | code

[7] Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression (无监督夜间图像增强：当层分解遇到光效抑制时)
paper | code

[6] Semantic-Sparse Colorization Network for Deep Exemplar-based Colorization (用于基于深度示例的着色的语义稀疏着色网络)
paper

[5] Geometry-aware Single-image Full-body Human Relighting (几何感知单图像全身人体重新照明)
paper

[4] Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion (单目全景深度补全的多模态蒙面预训练)
paper

[3] PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation (PanoFormer：用于室内 360 深度估计的全景变压器)
paper

[2] SESS: Saliency Enhancing with Scaling and Sliding (SESS：通过缩放和滑动增强显着性)
paper

[1] RigNet: Repetitive Image Guided Network for Depth Completion (RigNet：用于深度补全的重复图像引导网络)
paper

图像去阴影/去反射(Image Shadow Removal/Image Reflection Removal)

[1] Deep Portrait Delighting (深度人像去光)

paper

图像去噪(Image Denoising/Deblurring/Dehazing)

[3] Perceiving and Modeling Density is All You Need for Image Dehazing (感知和建模密度是图像去雾所需的全部) (Oral)
paper |code

[2] Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance (来自模糊的动画：具有运动引导的多模态模糊分解)
paper | code

[1] Deep Semantic Statistics Matching (D2SM) Denoising Network (深度语义统计匹配（D2SM）去噪网络)
paper

图像外推(Image Outpainting)

[1] Outpainting by Queries (通过查询进行外推)
paper | code

风格迁移(Style Transfer)

[1] CCPL: Contrastive Coherence Preserving Loss for Versatile Style Transfer (CCPL：通用风格迁移的对比相干性保留损失) (Oral)
paper | code

视频编辑(Video Editing)

[3] AlphaVC: High-Performance and Efficient Learned Video Compression (AlphaVC：高性能和高效的学习视频压缩)

paper

[2] Improving the Perceptual Quality of 2D Animation Interpolation (提高二维动画插值的感知质量)
paper | code

[1] Real-Time Intermediate Flow Estimation for Video Frame Interpolation(视频帧插值的实时中间流估计)
paper | code

视频修复(Video Inpainting)

[1] Error Compensation Framework for Flow-Guided Video Inpainting (流引导视频修复的误差补偿框架)
paper

视频去模糊(Video Deblurring)

[2] Event-guided Deblurring of Unknown Exposure Time Videos (未知曝光时间视频的事件引导去模糊) (Oral)

paper

[1] Efficient Video Deblurring Guided by Motion Magnitude (由运动幅度引导的高效视频去模糊)

paper | code

行为识别/行为识别/动作识别/检测/分割(Action/Activity Recognition)

[4] GaitEdge: Beyond Plain End-to-end Gait Recognition for Better Practicality (GaitEdge：超越普通的端到端步态识别，提高实用性)
paper | code

[3] Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition (用于跨域 3D 动作识别的协作域共享和特定于目标的特征聚类)
paper | code

[2] ReAct: Temporal Action Detection with Relational Queries (ReAct：使用关系查询的时间动作检测)
paper | code

[1] Hunting Group Clues with Transformers for Social Group Activity Recognition (用Transformers寻找群体线索用于社会群体活动识别)
paper

行人重识别/检测(Re-Identification/Detection)

[1] PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification(PASS：用于人员重新识别的部分感知自我监督预训练)
paper | code

视频理解(Video Understanding)

[1] GraphVid: It Only Takes a Few Nodes to Understand a Video (GraphVid：只需几个节点即可理解视频) (Oral)
paper

图像/视频检索(Image/Video Retrieval)

[6] Can Shuffling Video Benefit Temporal Bias Problem: A Novel Training Framework for Temporal Grounding (打乱的视频是否有益于时间偏差问题：一种新的时间接地训练框架)

paper |code

[5] Feature Representation Learning for Unsupervised Cross-domain Image Retrieval (无监督跨域图像检索的特征表示学习)
paper | code

[4] LocVTP: Video-Text Pre-training for Temporal Localization (LocVTP：时间定位的视频文本预训练)
paper | code

[3] Deep Hash Distillation for Image Retrieval (用于图像检索的深度哈希蒸馏)
paper | code

[2] TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval (TS2-Net：用于文本视频检索的令牌移位和选择转换器)
paper | code

[1] Lightweight Attentional Feature Fusion: A New Baseline for Text-to-Video Retrieval (轻量级注意力特征融合：文本到视频检索的新基线)
paper

光流/运动估计(Flow/Motion Estimation)

[1] Deep 360∘ Optical Flow Estimation Based on Multi-Projection Fusion (基于多投影融合的深度360∘光流估计)

paper

视觉定位/位姿估计(Visual Localization/Pose Estimation)

[4] Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction (被忽视的姿势实际上是有意义的：为人体运动预测提炼特权知识)

paper

[3] 3D Interacting Hand Pose Estimation by Hand De-occlusion and Removal (通过手部去遮挡和移除的 3D 交互手部姿势估计)

paper | code

[2] Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration (基于隐式空间校准的 Transformer 的弱监督目标定位)
[paper] (https://arxiv.org/abs/2207.10447) | code

[1] Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks (使用自监督深度先验变形网络的类别级 6D 对象姿势和大小估计)
paper | code

深度估计(Depth Estimation)

[1] Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches ((使用最优对抗补丁对单目深度估计进行物理攻击))
paper

人脸识别/检测(Facial Recognition/Detection)

[1] Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguation (通过场景消歧实现种族无偏肤色估计)

paper | code

人脸识别/检测(Facial Recognition/Detection)

[1] MoFaNeRF: Morphable Facial Neural Radiance Field (MoFaNeRF：可变形面部神经辐射场)

paper |code

三维重建(3D Reconstruction)

[1] DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Cameras (DiffuStereo：使用稀疏相机通过基于扩散的立体进行高质量人体重建)
paper

场景重建/视图合成/新视角合成(Novel View Synthesis)

[1] Sem2NeRF: Converting Single-View Semantic Masks to Neural Radiance Fields (Sem2NeRF：将单视图语义掩码转换为神经辐射场)
paper | code

文本检测/识别/理解(Text Detection/Recognition/Understanding)

[5] Toward Understanding WordArt: Corner-Guided Transformer for Scene Text Recognition (了解艺术字：用于场景文本识别的角引导转换器) (Oral)

paper | code

[4] Contextual Text Block Detection towards Scene Text Understanding (面向场景文本理解的上下文文本块检测)

paper

[3] PromptDet: Towards Open-vocabulary Detection using Uncurated Images (PromptDet：使用未经处理的图像进行开放词汇检测)
paper |code

[2] End-to-End Video Text Spotting with Transformer (使用 Transformer 的端到端视频文本定位) (Oral)
paper | code

[1] Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting (用于经济高效的端到端文本定位的动态低分辨率蒸馏)
paper | code

GAN/生成式/对抗式(GAN/Generative/Adversarial)

[7] Learning Energy-Based Models With Adversarial Training (通过对抗训练学习基于能量的模型)

paper | code

[6] Adaptive Image Transformations for Transfer-based Adversarial Attack (基于传输的对抗性攻击的自适应图像转换)
paper

[5] Generative Multiplane Images: Making a 2D GAN 3D-Aware (生成多平面图像：让一个2D GAN变得3D感知)
paper | code

[4] Eliminating Gradient Conflict in Reference-based Line-Art Colorization (消除基于参考的艺术线条着色中的梯度冲突)
paper | code

[3] WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generation (WaveGAN：用于高保真少镜头图像生成的频率感知 GAN)
paper | code

[2] FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs (FakeCLR：探索对比学习以解决数据高效 GAN 中的潜在不连续性)
paper | code

[1] UniCR: Universally Approximated Certified Robustness via Randomized Smoothing (UniCR：通过随机平滑获得普遍近似的认证鲁棒性)
paper

图像生成/图像合成(Image Generation/Image Synthesis)

[1] PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation (PixelFolder：用于图像生成的高效渐进式像素合成网络)

paper | code

视觉预测(Vision-based Prediction)

[1] D2-TPred: Discontinuous Dependency for Trajectory Prediction under Traffic Lights (D2-TPred：交通灯下轨迹预测的不连续依赖)
paper | code

Transformer

[5] Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding (用于长期 4D 点云视频理解的 Point Primitive Transformer)

paper

[4] Improving Vision Transformers by Revisiting High-frequency Components (通过重新审视高频组件来改进视觉变压器)

paper | code

[3] Transformer with Implicit Edges for Particle-based Physics Simulation (用于基于粒子的物理模拟的隐式边缘变压器)

paper | code

[2] ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer (ScalableViT：重新思考 Vision Transformer 面向上下文的泛化)
paper | code

[1] Visual Prompt Tuning (视觉提示调整)
paper | code

神经网络架构搜索(NAS)

[3] ScaleNet: Searching for the Model to Scale (ScaleNet：搜索要扩展的模型)
paper | code

[2] Ensemble Knowledge Guided Sub-network Search and Fine-tuning for Filter Pruning (集成知识引导的子网络搜索和过滤器修剪微调)
paper | code

[1] EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs (EAGAN：GAN 的高效两阶段进化架构搜索)
paper | code

归一化/正则化(Batch Normalization)

[1] Fine-grained Data Distribution Alignment for Post-Training Quantization (训练后量化的细粒度数据分布对齐) (Oral)
paper | code

22. 图像特征提取与匹配(Image feature extraction and matching)

[1] Unsupervised Deep Multi-Shape Matching (无监督深度多形状匹配)
paper

噪声标签(Noisy Label)

[1] Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection (通过有效的转移矩阵估计学习噪声标签以对抗标签错误校正)
paper

长尾分布(Long-Tailed Distribution)

[2] Long-tailed Instance Segmentation using Gumbel Optimized Loss (使用 Gumbel 优化损失的长尾实例分割)

paper | code

[1] Identifying Hard Noise in Long-Tailed Sample Distribution (识别长尾样本分布中的硬噪声) (Oral)

paper|code

知识蒸馏(Knowledge Distillation)

[3] Prune Your Model Before Distill It (在蒸馏之前修剪你的模型)

paper|code

[2] Efficient One Pass Self-distillation with Zipf's Label Smoothing (使用 Zipf 的标签平滑实现高效的单程自蒸馏)

paper | code

[1] Knowledge Condensation Distillation (知识浓缩蒸馏)
paper | code

半监督学习/弱监督学习/无监督学习/自监督学习(Self-supervised Learning/Semi-supervised Learning)

[8] Acknowledging the Unknown for Multi-label Learning with Single Positive Labels (用单个正标签承认未知的多标签学习)

paper | code

[7] W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection (W2N：目标检测从弱监督切换到嘈杂监督)

paper | code

[6] CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation (CA-SSL：用于检测和分割的与类别无关的半监督学习)
paper | code

[5] FedX: Unsupervised Federated Learning with Cross Knowledge Distillation (FedX：具有交叉知识蒸馏的无监督联合学习)
paper

[4] Synergistic Self-supervised and Quantization Learning (协同自监督和量化学习)
paper | code

[3] Contrastive Deep Supervision (对比深度监督)
paper | code

[2] Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection (稠密教师：用于半监督目标检测的稠密伪标签)
paper

[1] Image Coding for Machines with Omnipotent Feature Learning (具有全能特征学习的机器的图像编码)
paper

视觉-语言（Vision-language）

[2] Language Matters: A Weakly Supervised Vision-Language Pre-training Approach for Scene Text Detection and Spotting (语言问题：用于场景文本检测和识别的弱监督视觉语言预训练方法) (Oral)

paper

[1] Contrastive Vision-Language Pre-training with Limited Resources (资源有限的对比视觉语言预训练)
paper | code

其他

Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets

• 论文：https://arxiv.org/abs/2007.09654
• 代码：https://github.com/wutong16/DistributionBalancedLoss

A Generic Visualization Approach for Convolutional Neural Networks

• 论文：https://arxiv.org/abs/2007.09748

• 代码：https://github.com/ahmdtaha/constrained_attention_filter

Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches

• 主页：https://williamyang1991.github.io/projects/ECCV2020
• 论文：https://arxiv.org/abs/2001.02890
• 代码：https://github.com/TAMU-VITA/DeepPS

GIQA: Generated Image Quality Assessment

• 论文：https://arxiv.org/abs/2003.08932
• 代码：https://github.com/cientgu/GIQA

Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling

• 主页：http://structured3d-dataset.org
• 论文：https://arxiv.org/abs/1908.00222
• 代码：https://github.com/bertjiazheng/Structured3D

AiR: Attention with Reasoning Capability

• 论文：暂无

• 代码：https://github.com/szzexpoi/AiR

• 数据集：https://github.com/szzexpoi/AiR

Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasets

• 论文/Paper: http://arxiv.org/pdf/2207.01573
• 代码/Code: None

GraphVid: It Only Takes a Few Nodes to Understand a Video

• 论文/Paper: http://arxiv.org/pdf/2207.01375
• 代码/Code: None

Target-absent Human Attention

• 论文/Paper: http://arxiv.org/pdf/2207.01166
• 代码/Code: None

Lottery Ticket Hypothesis for Spiking Neural Networks

• 论文/Paper: http://arxiv.org/pdf/2207.01382
• 代码/Code: None

Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality

• 论文/Paper: http://arxiv.org/abs/2207.02119
• 代码/Code: https://github.com/kingjamessong/orthoimprovecond

AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture

• 论文/Paper: http://arxiv.org/abs/2207.02031
• 代码/Code: https://github.com/lizhe00/AvatarCap.

DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images

• 论文/Paper: http://arxiv.org/abs/2207.02025
• 代码/Code: None

Learning Local Implicit Fourier Representation for Image Warping

• 论文/Paper: http://arxiv.org/abs/2207.01831
• 代码/Code: https://github.com/jaewon-lee-b/ltew

SESS: Saliency Enhancing with Scaling and Sliding

• 论文/Paper: http://arxiv.org/abs/2207.01769
• 代码/Code: https://github.com/neouyghur/sess

TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts

• 论文/Paper: http://arxiv.org/abs/2207.01696
• 代码/Code: None

DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.02606
• 代码/Code: None

FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Sampling

• 论文/Paper: http://arxiv.org/pdf/2207.02595
• 代码/Code: https://github.com/timothyhtimothy/fast-vqa

Towards Realistic Semi-Supervised Learning

• 论文/Paper: http://arxiv.org/pdf/2207.02269
• 代码/Code: None

OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised Learning

• 论文/Paper: http://arxiv.org/pdf/2207.02261
• 代码/Code: None

Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning

• 论文/Paper: http://arxiv.org/pdf/2207.02598
• 代码/Code: None

Factorizing Knowledge in Neural Networks

• 论文/Paper: http://arxiv.org/pdf/2207.03337
• 代码/Code: None

SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning

• 论文/Paper: http://arxiv.org/pdf/2207.03677
• 代码/Code: https://github.com/RICE-EIC/SuperTickets.

Video Dialog as Conversation about Objects Living in Space-Time

• 论文/Paper: http://arxiv.org/pdf/2207.03656
• 代码/Code: https://github.com/hoanganhpham1006/COST

Demystifying Unsupervised Semantic Correspondence Estimation

• 论文/Paper: http://arxiv.org/pdf/2207.05054
• 代码/Code: None

A Closer Look at Invariances in Self-supervised Pre-training for 3D Vision

• 论文/Paper: http://arxiv.org/pdf/2207.04997
• 代码/Code: None

DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization

• 论文/Paper: http://arxiv.org/pdf/2207.04788
• 代码/Code: None

Batch-efficient EigenDecomposition for Small and Medium Matrices

• 论文/Paper: http://arxiv.org/pdf/2207.04228
• 代码/Code: None

Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Space

• 论文/Paper: http://arxiv.org/pdf/2207.04161
• 代码/Code: None

Camera Pose Auto-Encoders for Improving Pose Regression

• 论文/Paper: http://arxiv.org/pdf/2207.05530
• 代码/Code: https://github.com/yolish/camera-pose-auto-encoders

Synergistic Self-supervised and Quantization Learning

• 论文/Paper: http://arxiv.org/pdf/2207.05432
• 代码/Code: https://github.com/megvii-research/SSQL-ECCV2022

Frequency Domain Model Augmentation for Adversarial Attack

• 论文/Paper: http://arxiv.org/pdf/2207.05382
• 代码/Code: https://github.com/yuyang-long/ssa

Organic Priors in Non-Rigid Structure from Motion

• 论文/Paper: http://arxiv.org/pdf/2207.06262
• 代码/Code: None

Unsupervised Visual Representation Learning by Synchronous Momentum Grouping

• 论文/Paper: http://arxiv.org/pdf/2207.06167
• 代码/Code: None

Learning Implicit Templates for Point-Based Clothed Human Modeling

• 论文/Paper: http://arxiv.org/pdf/2207.06955
• 代码/Code: https://github.com/jsnln/fite

BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks

• 论文/Paper: http://arxiv.org/pdf/2207.06873
• 代码/Code: https://github.com/explainableml/bayescap

Lipschitz Continuity Retained Binary Neural Network

• 论文/Paper: http://arxiv.org/pdf/2207.06540
• 代码/Code: https://github.com/42shawn/lcr_bnn

3D Instances as 1D Kernels

• 论文/Paper: http://arxiv.org/pdf/2207.07372
• 代码/Code: https://github.com/W1zheng/DKNet

ScaleNet: Searching for the Model to Scale

• 论文/Paper: http://arxiv.org/pdf/2207.07267
• 代码/Code: https://github.com/luminolx/ScaleNet

Rethinking Data Augmentation for Robust Visual Question Answering

• 论文/Paper: http://arxiv.org/pdf/2207.08739
• 代码/Code: https://github.com/ItemZheng/KDDAug

Semantic Novelty Detection via Relational Reasoning

• 论文/Paper: http://arxiv.org/pdf/2207.08699
• 代码/Code: None

Label2Label: A Language Modeling Framework for Multi-Attribute Learning

• 论文/Paper: http://arxiv.org/pdf/2207.08677
• 代码/Code: https://github.com/Li-Wanhua/Label2Label.

Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes

• 论文/Paper: http://arxiv.org/pdf/2207.08656
• 代码/Code: https://github.com/UncleMEDM/InstPIFu

Class-incremental Novel Class Discovery

• 论文/Paper: http://arxiv.org/pdf/2207.08605
• 代码/Code: https://github.com/OatmealLiu/class-iNCD

MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects

• 论文/Paper: http://arxiv.org/pdf/2207.08403
• 代码/Code: None

SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement

• 论文/Paper: http://arxiv.org/pdf/2207.08351
• 代码/Code: None

Learning with Recoverable Forgetting

• 论文/Paper: http://arxiv.org/pdf/2207.08224
• 代码/Code: None

Zero-Shot Temporal Action Detection via Vision-Language Prompting

• 论文/Paper: http://arxiv.org/pdf/2207.08184
• 代码/Code: https://github.com/sauradip/STALE

Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal

• 论文/Paper: http://arxiv.org/pdf/2207.08178
• 代码/Code: None

FashionViL: Fashion-Focused Vision-and-Language Representation Learning

• 论文/Paper: http://arxiv.org/pdf/2207.08150
• 代码/Code: https://github.com/BrandonHanx/mmf.

E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context

• 论文/Paper: http://arxiv.org/pdf/2207.08132
• 代码/Code: https://github.com/kyleleey/E-NeRV.

Neural Color Operators for Sequential Image Retouching

• 论文/Paper: http://arxiv.org/pdf/2207.08080
• 代码/Code: https://github.com/amberwangyili/neurop

Semi-Supervised Keypoint Detector and Descriptor for Retinal Image Matching

• 论文/Paper: http://arxiv.org/pdf/2207.07932
• 代码/Code: None

JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes

• 论文/Paper: http://arxiv.org/pdf/2207.07895
• 代码/Code: at~\href{https://github.com/sunnyHelen/JPerceiver}{https://github.com/sunnyHelen/JPerceiver}.

You Should Look at All Objects

• 论文/Paper: http://arxiv.org/pdf/2207.07889
• 代码/Code: None

NeFSAC: Neurally Filtered Minimal Samples

• 论文/Paper: http://arxiv.org/pdf/2207.07872
• 代码/Code: https://github.com/cavalli1234/NeFSAC.

CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAS

• 论文/Paper: http://arxiv.org/pdf/2207.07868
• 代码/Code: https://github.com/walkerning/aw_nas.

Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations

• 论文/Paper: http://arxiv.org/pdf/2207.07826
• 代码/Code: https://github.com/WentaoChen0813/CDCS-FSL

Self-calibrating Photometric Stereo by Neural Inverse Rendering

• 论文/Paper: http://arxiv.org/pdf/2207.07815
• 代码/Code: https://github.com/junxuan-li/SCPS-NIR

Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection

• 论文/Paper: http://arxiv.org/pdf/2207.07783
• 代码/Code: https://github.com/SRA2/SPELL

Towards Understanding The Semidefinite Relaxations of Truncated Least-Squares in Robust Rotation Search

• 论文/Paper: http://arxiv.org/pdf/2207.08350
• 代码/Code: None

PoserNet: Refining Relative Camera Poses Exploiting Object Detections

• 论文/Paper: http://arxiv.org/pdf/2207.09445
• 代码/Code: https://github.com/IIT-PAVIS/PoserNet

Geometric Features Informed Multi-person Human-object Interaction Recognition in Videos

• 论文/Paper: http://arxiv.org/pdf/2207.09425
• 代码/Code: None

Deep Semantic Statistics Matching (D2SM) Denoising Network

• 论文/Paper: http://arxiv.org/pdf/2207.09302
• 代码/Code: None

3D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transform

• 论文/Paper: http://arxiv.org/pdf/2207.09291
• 代码/Code: https://github.com/Starrah/DMH-Net

NDF: Neural Deformable Fields for Dynamic Human Modelling

• 论文/Paper: http://arxiv.org/pdf/2207.09193
• 代码/Code: None

Self-Supervision Can Be a Good Few-Shot Learner

• 论文/Paper: http://arxiv.org/pdf/2207.09176
• 代码/Code: https://github.com/bbbdylan/unisiam

ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild

• 论文/Paper: http://arxiv.org/pdf/2207.09137
• 代码/Code: https://github.com/bytedance/particle-sfm.

MHR-Net: Multiple-Hypothesis Reconstruction of Non-Rigid Shapes from 2D Views

• 论文/Paper: http://arxiv.org/pdf/2207.09086
• 代码/Code: None

SelectionConv: Convolutional Neural Networks for Non-rectilinear Image Data

• 论文/Paper: http://arxiv.org/pdf/2207.08979
• 代码/Code: None

Prior-Guided Adversarial Initialization for Fast Adversarial Training

• 论文/Paper: http://arxiv.org/pdf/2207.08859
• 代码/Code: https://github.com/jiaxiaojunQAQ/FGSM-PGI.

Prior Knowledge Guided Unsupervised Domain Adaptation

• 论文/Paper: http://arxiv.org/pdf/2207.08877
• 代码/Code: https://github.com/tsun/KUDA

Discover and Mitigate Unknown Biases with Debiasing Alternate Networks

• 论文/Paper: http://arxiv.org/pdf/2207.10077
• 代码/Code: https://github.com/zhihengli-UR/DebiAN

Difficulty-Aware Simulator for Open Set Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.10024
• 代码/Code: https://github.com/wjun0830/difficulty-aware-simulator

Tailoring Self-Supervision for Supervised Learning

• 论文/Paper: http://arxiv.org/pdf/2207.10023
• 代码/Code: https://github.com/wjun0830/localizable-rotation

Overcoming Shortcut Learning in a Target Domain by Generalizing Basic Visual Factors from a Source Domain

• 论文/Paper: http://arxiv.org/pdf/2207.10002
• 代码/Code: https://github.com/boschresearch/sourcegen

Temporal and cross-modal attention for audio-visual zero-shot learning

• 论文/Paper: http://arxiv.org/pdf/2207.09966
• 代码/Code: https://github.com/explainableml/tcaf-gzsl

Telepresence Video Quality Assessment

• 论文/Paper: http://arxiv.org/pdf/2207.09956
• 代码/Code: None

Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing

• 论文/Paper: http://arxiv.org/pdf/2207.09935
• 代码/Code: None

Negative Samples are at Large: Leveraging Hard-distance Elastic Loss for Re-identification

• 论文/Paper: http://arxiv.org/pdf/2207.09884
• 代码/Code: None

Discrete-Constrained Regression for Local Counting Models

• 论文/Paper: http://arxiv.org/pdf/2207.09865
• 代码/Code: None

Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction

• 论文/Paper: http://arxiv.org/pdf/2207.09705
• 代码/Code: None

Efficient Meta-Tuning for Content-aware Neural Video Delivery

• 论文/Paper: http://arxiv.org/pdf/2207.09691
• 代码/Code: https://github.com/neural-video-delivery/emt-pytorch-eccv2022

Object-Compositional Neural Implicit Surfaces

• 论文/Paper: http://arxiv.org/pdf/2207.09686
• 代码/Code: https://github.com/qianyiwu/objsdf

Explaining Deepfake Detection by Analysing Image Matching

• 论文/Paper: http://arxiv.org/pdf/2207.09679
• 代码/Code: https://github.com/megvii-research/fst-matching

ERA: Expert Retrieval and Assembly for Early Action Prediction

• 论文/Paper: http://arxiv.org/pdf/2207.09675
• 代码/Code: None

Perspective Phase Angle Model for Polarimetric 3D Reconstruction

• 论文/Paper: http://arxiv.org/pdf/2207.09629
• 代码/Code: https://github.com/gcchen97/ppa4p3d

Explicit Image Caption Editing

• 论文/Paper: http://arxiv.org/pdf/2207.09625
• 代码/Code: https://github.com/baaaad/ece

Unsupervised Deep Multi-Shape Matching

• 论文/Paper: http://arxiv.org/pdf/2207.09610
• 代码/Code: None

Contributions of Shape, Texture, and Color in Visual Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.09510
• 代码/Code: https://github.com/gyhandy/humanoid-vision-engine

Novel Class Discovery without Forgetting

• 论文/Paper: http://arxiv.org/pdf/2207.10659
• 代码/Code: None

Approximate Differentiable Rendering with Algebraic Surfaces

• 论文/Paper: http://arxiv.org/pdf/2207.10606
• 代码/Code: None

FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling

• 论文/Paper: http://arxiv.org/pdf/2207.10392
• 代码/Code: None

Error Compensation Framework for Flow-Guided Video Inpainting

• 论文/Paper: http://arxiv.org/pdf/2207.10391
• 代码/Code: None

NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.10388
• 代码/Code: None

Temporal Saliency Query Network for Efficient Video Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.10379
• 代码/Code: None

UFO: Unified Feature Optimization

• 论文/Paper: http://arxiv.org/pdf/2207.10341
• 代码/Code: None

OIMNet++: Prototypical Normalization and Localization-aware Learning for Person Search

• 论文/Paper: http://arxiv.org/pdf/2207.10320
• 代码/Code: None

Towards Accurate Open-Set Recognition via Background-Class Regularization

• 论文/Paper: http://arxiv.org/pdf/2207.10287
• 代码/Code: None

Grounding Visual Representations with Texts for Domain Generalization

• 论文/Paper: http://arxiv.org/pdf/2207.10285
• 代码/Code: https://github.com/mswzeus/gvrt

SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks

• 论文/Paper: http://arxiv.org/pdf/2207.10237
• 代码/Code: https://github.com/apple/ml-spin

MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis

• 论文/Paper: http://arxiv.org/pdf/2207.10228
• 代码/Code: None

On Label Granularity and Object Localization

• 论文/Paper: http://arxiv.org/pdf/2207.10225
• 代码/Code: https://github.com/visipedia/inat_loc

Spotting Temporally Precise, Fine-Grained Events in Video

• 论文/Paper: http://arxiv.org/pdf/2207.10213
• 代码/Code: None

Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles

• 论文/Paper: http://arxiv.org/pdf/2207.10172
• 代码/Code: None

GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning

• 论文/Paper: http://arxiv.org/pdf/2207.10158
• 代码/Code: https://github.com/seleucia/goca

Visual Knowledge Tracing

• 论文/Paper: http://arxiv.org/pdf/2207.10157
• 代码/Code: https://github.com/nkondapa/visualknowledgetracing

Tackling Long-Tailed Category Distribution Under Domain Shifts

• 论文/Paper: http://arxiv.org/pdf/2207.10150
• 代码/Code: https://github.com/guxiao0822/lt-ds

Latent Discriminant deterministic Uncertainty

• 论文/Paper: http://arxiv.org/pdf/2207.10130
• 代码/Code: https://github.com/ensta-u2is/ldu

Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance

• 论文/Paper: http://arxiv.org/pdf/2207.10123
• 代码/Code: https://github.com/zzh-tech/Animation-from-Blur.

Bitwidth-Adaptive Quantization-Aware Neural Network Training: A Meta-Learning Approach

• 论文/Paper: http://arxiv.org/pdf/2207.10188
• 代码/Code: None

Structural Causal 3D Reconstruction

• 论文/Paper: http://arxiv.org/pdf/2207.10156
• 代码/Code: None

AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation

• 论文/Paper: http://arxiv.org/pdf/2207.10141
• 代码/Code: None

Continual Variational Autoencoder Learning via Online Cooperative Memorization

• 论文/Paper: http://arxiv.org/pdf/2207.10131
• 代码/Code: https://github.com/dtuzi123/ovae

Panoptic Scene Graph Generation

• 论文/Paper: http://arxiv.org/pdf/2207.11247
• 代码/Code: https://github.com/Jingkang50/OpenPSG

Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay

• 论文/Paper: http://arxiv.org/pdf/2207.11213
• 代码/Code: None

POP: Mining POtential Performance of new fashion products via webly cross-modal query expansion

• 论文/Paper: http://arxiv.org/pdf/2207.11001
• 代码/Code: https://github.com/HumaticsLAB/POP-Mining-POtential-Performance

Few-shot Object Counting and Detection

• 论文/Paper: http://arxiv.org/pdf/2207.10988
• 代码/Code: https://github.com/VinAIResearch/Counting-DETR

Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly Detection

• 论文/Paper: http://arxiv.org/pdf/2207.10948
• 代码/Code: https://github.com/Beyond-Zw/DLAN-AC.

My View is the Best View: Procedure Learning from Egocentric Videos

• 论文/Paper: http://arxiv.org/pdf/2207.10883
• 代码/Code: https://github.com/Sid2697/EgoProceL-egocentric-procedure-learning

Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation

• 论文/Paper: http://arxiv.org/pdf/2207.10856
• 代码/Code: https://github.com/Hongbin98/ProCA.git

MeshLoc: Mesh-Based Visual Localization

• 论文/Paper: http://arxiv.org/pdf/2207.10762
• 代码/Code: None

MemSAC: Memory Augmented Sample Consistency for Large Scale Domain Adaptation

• 论文/Paper: http://arxiv.org/pdf/2207.12389
• 代码/Code: None

Deforming Radiance Fields with Cages

• 论文/Paper: http://arxiv.org/pdf/2207.12298
• 代码/Code: None

Equivariance and Invariance Inductive Bias for Learning from Insufficient Data

• 论文/Paper: http://arxiv.org/pdf/2207.12258
• 代码/Code: https://github.com/Wangt-CN/EqInv

Black-box Few-shot Knowledge Distillation

• 论文/Paper: http://arxiv.org/pdf/2207.12106
• 代码/Code: https://github.com/nphdang/FS-BBT

Balancing Stability and Plasticity through Advanced Null Space in Continual Learning

• 论文/Paper: http://arxiv.org/pdf/2207.12061
• 代码/Code: None

Optimal Boxes: Boosting End-to-End Scene Text Recognition by Adjusting Annotated Bounding Boxes via Reinforcement Learning

• 论文/Paper: http://arxiv.org/pdf/2207.11934
• 代码/Code: None

NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing

• 论文/Paper: http://arxiv.org/pdf/2207.11911
• 代码/Code: None

Domain Adaptive Person Search

• 论文/Paper: http://arxiv.org/pdf/2207.11898
• 代码/Code: https://github.com/caposerenity/DAPS.

VizWiz-FewShot: Locating Objects in Images Taken by People With Visual Impairments

• 论文/Paper: http://arxiv.org/pdf/2207.11810
• 代码/Code: None

Label-Guided Auxiliary Training Improves 3D Object Detector

• 论文/Paper: http://arxiv.org/pdf/2207.11753
• 代码/Code: None

Combining Internal and External Constraints for Unrolling Shutter in Videos

• 论文/Paper: http://arxiv.org/pdf/2207.11725
• 代码/Code: None

TIPS: Text-Induced Pose Synthesis

• 论文/Paper: http://arxiv.org/pdf/2207.11718
• 代码/Code: None

Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes

• 论文/Paper: http://arxiv.org/pdf/2207.11707
• 代码/Code: None

Learning Graph Neural Networks for Image Style Transfer

• 论文/Paper: http://arxiv.org/pdf/2207.11681
• 代码/Code: None

Contrastive Monotonic Pixel-Level Modulation

• 论文/Paper: http://arxiv.org/pdf/2207.11517
• 代码/Code: https://github.com/lukun199/MonoPix.

CompNVS: Novel View Synthesis with Scene Completion

• 论文/Paper: http://arxiv.org/pdf/2207.11467
• 代码/Code: None

When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.11463
• 代码/Code: https://github.com/LBH1024/CAN.

Meta Spatio-Temporal Debiasing for Video Scene Graph Generation

• 论文/Paper: http://arxiv.org/pdf/2207.11441
• 代码/Code: None

3D Shape Sequence of Human Comparison and Classification using Current and Varifolds

• 论文/Paper: http://arxiv.org/pdf/2207.12485
• 代码/Code: https://github.com/cristal-3dsam/humancomparisonvarifolds

NewsStories: Illustrating articles with visual summaries

• 论文/Paper: http://arxiv.org/pdf/2207.13061
• 代码/Code: https://github.com/newsstoriesdata/newsstories.github.io

Efficient One Pass Self-distillation with Zipf's Label Smoothing

• 论文/Paper: http://arxiv.org/pdf/2207.12980
• 代码/Code: https://github.com/megvii-research/zipfls

AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction

• 论文/Paper: http://arxiv.org/pdf/2207.12909
• 代码/Code: None

Static and Dynamic Concepts for Self-supervised Video Representation Learning

• 论文/Paper: http://arxiv.org/pdf/2207.12795
• 代码/Code: None

Learning Hierarchy Aware Features for Reducing Mistake Severity

• 论文/Paper: http://arxiv.org/pdf/2207.12646
• 代码/Code: https://github.com/07agarg/haf

Translating a Visual LEGO Manual to a Machine-Executable Plan

• 论文/Paper: http://arxiv.org/pdf/2207.12572
• 代码/Code: None

Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning

• 论文/Paper: http://arxiv.org/pdf/2207.12535
• 代码/Code: https://github.com/xinleihe/semi-leak

Trainability Preserving Neural Structured Pruning

• 论文/Paper: http://arxiv.org/pdf/2207.12534
• 代码/Code: https://github.com/mingsun-tse/tpp

Shift-tolerant Perceptual Similarity Metric

• 论文/Paper: http://arxiv.org/pdf/2207.13686
• 代码/Code: http://github.com/abhijay9/ShiftTolerant-LPIPS/

Abstracting Sketches through Simple Primitives

• 论文/Paper: http://arxiv.org/pdf/2207.13543
• 代码/Code: https://github.com/ExplainableML/sketch-primitives.

AutoTransition: Learning to Recommend Video Transition Effects

• 论文/Paper: http://arxiv.org/pdf/2207.13479
• 代码/Code: https://github.com/acherstyx/AutoTransition

Hardly Perceptible Trojan Attack against Neural Networks with Bit Flips

• 论文/Paper: http://arxiv.org/pdf/2207.13417
• 代码/Code: https://github.com/jiawangbai/HPT

Identifying Hard Noise in Long-Tailed Sample Distribution

• 论文/Paper: http://arxiv.org/pdf/2207.13378
• 代码/Code: https://github.com/yxymessi/H2E-Framework

One-Trimap Video Matting

• 论文/Paper: http://arxiv.org/pdf/2207.13353
• 代码/Code: https://github.com/Hongje/OTVM

PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation

• 论文/Paper: http://arxiv.org/pdf/2207.13340
• 代码/Code: None

End-to-end Graph-constrained Vectorized Floorplan Generation with Panoptic Refinement

• 论文/Paper: http://arxiv.org/pdf/2207.13268
• 代码/Code: None

Spatiotemporal Self-attention Modeling with Temporal Patch Shift for Action Recognition

• 论文/Paper: http://arxiv.org/pdf/2207.13259
• 代码/Code: https://github.com/MartinXM/TPS

Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation

• 论文/Paper: http://arxiv.org/pdf/2207.13247
• 代码/Code: None

LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity

• 论文/Paper: http://arxiv.org/pdf/2207.13129
• 代码/Code: None

Initialization and Alignment for Adversarial Texture Optimization

• 论文/Paper: http://arxiv.org/pdf/2207.14289
• 代码/Code: None

Depth Field Networks for Generalizable Multi-view Scene Representation

• 论文/Paper: http://arxiv.org/pdf/2207.14287
• 代码/Code: None

Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection

• 论文/Paper: http://arxiv.org/pdf/2207.14192
• 代码/Code: https://github.com/enlighten0707/Body-Part-Map-for-Interactiveness.

Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images

• 论文/Paper: http://arxiv.org/pdf/2207.14067
• 代码/Code: None

Break and Make: Interactive Structural Understanding Using LEGO Bricks

• 论文/Paper: http://arxiv.org/pdf/2207.13738
• 代码/Code: https://github.com/aaronwalsman/ltron.

A Repulsive Force Unit for Garment Collision Handling in Neural Networks

• 论文/Paper: http://arxiv.org/pdf/2207.13871
• 代码/Code: None

Minimal Neural Atlas: Parameterizing Complex Surfaces with Minimal Charts and Distortion

• 论文/Paper: http://arxiv.org/pdf/2207.14782
• 代码/Code: https://github.com/low5545/minimal-neural-atlas

Can Shuffling Video Benefit Temporal Bias Problem: A Novel Training Framework for Temporal Grounding

• 论文/Paper: http://arxiv.org/pdf/2207.14698
• 代码/Code: https://github.com/haojc/ShufflingVideosForTSG.

AlphaVC: High-Performance and Efficient Learned Video Compression

• 论文/Paper: http://arxiv.org/pdf/2207.14678
• 代码/Code: None

WISE: Whitebox Image Stylization by Example-based Learning

• 论文/Paper: http://arxiv.org/pdf/2207.14606
• 代码/Code: None

Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels

• 论文/Paper: http://arxiv.org/pdf/2207.14476
• 代码/Code: None

Video Question Answering with Iterative Video-Text Co-Tokenization

• 论文/Paper: http://arxiv.org/pdf/2208.00934
• 代码/Code: None

S$^2$Contact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning

• 论文/Paper: http://arxiv.org/pdf/2208.00874
• 代码/Code: None

Skeleton-free Pose Transfer for Stylized 3D Characters

• 论文/Paper: http://arxiv.org/pdf/2208.00790
• 代码/Code: None

Improving Fine-Grained Visual Recognition in Low Data Regimes via Self-Boosting Attention Mechanism

• 论文/Paper: http://arxiv.org/pdf/2208.00617
• 代码/Code: https://github.com/GANPerf/SAM

SdAE: Self-distillated Masked Autoencoder

• 论文/Paper: http://arxiv.org/pdf/2208.00449
• 代码/Code: https://github.com/AbrahamYabo/SdAE.

Out-of-Distribution Detection with Semantic Mismatch under Masking

• 论文/Paper: http://arxiv.org/pdf/2208.00446
• 代码/Code: https://github.com/cure-lab/MOODCat

Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction

• 论文/Paper: http://arxiv.org/pdf/2208.00368
• 代码/Code: None

Revisiting the Critical Factors of Augmentation-Invariant Representation Learning

• 论文/Paper: http://arxiv.org/pdf/2208.00275
• 代码/Code: None

Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network

• 论文/Paper: http://arxiv.org/pdf/2208.00183
• 代码/Code: None

Few-Shot Class-Incremental Learning from an Open-Set Perspective

• 论文/Paper: http://arxiv.org/pdf/2208.00147
• 代码/Code: None

DAS: Densely-Anchored Sampling for Deep Metric Learning

• 论文/Paper: http://arxiv.org/pdf/2208.00119
• 代码/Code: https://github.com/lizhaoliu-Lec/DAS

Fast Two-step Blind Optical Aberration Correction

• 论文/Paper: http://arxiv.org/pdf/2208.00950
• 代码/Code: None

Negative Frames Matter in Egocentric Visual Query 2D Localization

• 论文/Paper: http://arxiv.org/pdf/2208.01949
• 代码/Code: https://github.com/facebookresearch/vq2d_cvpr

来源：

https://github.com/DWCTOD/ECCV2022-Papers-with-Code-Demo

https://github.com/extreme-assistant/ECCV2022-Paper-Code-Interpretation